fulltext_database
Access cached full-text content database (read-only).
How to use it
fulltext_database is exposed by the Zotero MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the fulltext_database tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL ZOTERO MCP LISTINGOther tools in Zotero MCP (21)
(required: list/search/get/stats), query, itemKeys, limit
Find items semantically similar to a given item.
Get details of a specific collection. Params: collectionKey (required).
Get items in a collection. Params: collectionKey (required), limit, offset.
Get all collections. Params: mode, limit, offset.
Unified content extraction: PDF full-text, notes, abstracts, webpage snapshots from items or specific attachments.
Get item abstract/summary. Params: itemKey (required), format (json/text).
Get complete metadata for a single item. Params: itemKey (required), mode.
Get subcollections. Params: collectionKey (required), limit, offset, recursive.
, attachmentKey, mode, include (pdf/attachments/notes/abstract/webpage), contentControl, format (json/text)
(required), topK, minScore, language (zh/en/all)
Search annotations by query, colors, or tags with intelligent ranking.
Search collections by name. Params: q, limit.
Full-text search across all document content with context snippets.
Advanced library search with multi-dimensional filtering, boolean operators, relevance scoring, and intelligent mode control.
AI-powered semantic search using embedding vectors. Finds conceptually related content even without exact keyword matches.
Get semantic search service status and index statistics. No parameters required.
Create new items or reparent existing attachments.
Update metadata fields on items (title, abstract, date, DOI, creators, etc.).
Create or modify Zotero notes. Supports Markdown auto-conversion to HTML.
Add, remove, or replace tags on items.